© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43951
    Prev
    Next
    INDEX
    Explanations

    mobile devices and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½Ĩæĺ¯ä½ł
    -0.07
    иÑİ
    -0.07
    (er
    -0.07
    èĢĮéĤ£
    -0.06
    egend
    -0.06
    _cmds
    -0.06
    agate
    -0.06
    ipu
    -0.06
    ativ
    -0.06
    æĦļ人
    -0.06
    POSITIVE LOGITS
    ull
    0.07
    unas
    0.07
    æīī
    0.07
    丼
    0.07
    inei
    0.07
    æĪijåºĶ该
    0.07
    ãģ¥ãģij
    0.06
    æŶåĢĻ
    0.06
    éĺģ
    0.06
    uno
    0.06
    Activations Density 0.003%

    No Known Activations